相关论文: sui-1: Grounded and Verifiable Long-Form Summariza…

Information extraction from regulatory documents using large language models presents critical trade-offs between performance and computational resources. We evaluated seven open-weight models (0.6B-70B parameters) on hydropower licensing…

Unlike extractive summarization, abstractive summarization has to fuse different parts of the source text, which inclines to create fake facts. Our preliminary study reveals nearly 30% of the outputs from a state-of-the-art neural…

Automatic summarization of legal case judgements, which are known to be long and complex, has traditionally been tried via extractive summarization models. In recent years, generative models including abstractive summarization models and…

Automatic summarisation is a popular approach to reduce a document to its main arguments. Recent research in the area has focused on neural approaches to summarisation, which can be very data-hungry. However, few large datasets exist and…

Recent advancements in text summarization, particularly with the advent of Large Language Models (LLMs), have shown remarkable performance. However, a notable challenge persists as a substantial number of automatically-generated summaries…

Evaluating the truthfulness of online content is critical for combating misinformation. This study examines the efficiency and effectiveness of crowdsourced truthfulness assessments through a comparative analysis of two approaches: one…

Data-driven approaches to sequence-to-sequence modelling have been successfully applied to short text summarization of news articles. Such models are typically trained on input-summary pairs consisting of only a single or a few sentences,…

Large Language Models (LLMs) have shown significant promise in automated theorem proving, yet progress is often constrained by the scarcity of diverse and high-quality formal language data. To address this issue, we introduce…

A commonly observed problem with the state-of-the art abstractive summarization models is that the generated summaries can be factually inconsistent with the input documents. The fact that automatic summarization may produce…

The availability of a vast array of research papers in any area of study, necessitates the need of automated summarisation systems that can present the key research conducted and their corresponding findings. Scientific paper summarisation…

Multimodal summarization aims to generate a concise summary based on the input text and image. However, the existing methods potentially suffer from unfactual output. To evaluate the factuality of multimodal summarization models, we propose…

While recent work in abstractive summarization has resulted in higher scores in automatic metrics, there is little understanding on how these systems combine information taken from multiple document sentences. In this paper, we analyze the…

Many-to-many summarization (M2MS) aims to process documents in any language and generate the corresponding summaries also in any language. Recently, large language models (LLMs) have shown strong multi-lingual abilities, giving them the…

Cross-lingual text summarization aims at generating a document summary in one language given input in another language. It is a practically important but under-explored task, primarily due to the dearth of available data. Existing methods…

Large language models (LLMs) often hallucinate, yet most existing fact-checking methods treat factuality evaluation as a binary classification problem, offering limited interpretability and failing to capture fine-grained error types. In…

Evaluating the performance of Large Language Models (LLMs) is a critical yet challenging task, particularly when aiming to avoid subjective assessments. This paper proposes a framework for leveraging subjective metrics derived from the…

Large language models (LLMs) still produce plausible-sounding but ungrounded factual claims, a problem that worsens in multi-turn dialogue as context grows and early errors cascade. We introduce $\textbf{HalluHard}$, a challenging…

Interpretability and efficiency are two important considerations for the adoption of neural automatic metrics. In this work, we develop strong-performing automatic metrics for reference-based summarization evaluation, based on a two-stage…

This paper presents a pipeline integrating fine-tuned large language models (LLMs) with named entity recognition (NER) for efficient domain-specific text summarization and tagging. The authors address the challenge posed by rapidly evolving…

Summarization datasets are often assembled either by scraping naturally occurring public-domain summaries -- which are nearly always in difficult-to-work-with technical domains -- or by using approximate heuristics to extract them from…